Incorporating Interpretable Output Constraints in Bayesian Neural Networks.
Wanqian YangLars LorchMoritz A. GrauleHimabindu LakkarajuFinale Doshi-VelezPublished in: NeurIPS (2020)
Keyphrases
- neural network
- constrained optimization
- pattern recognition
- genetic algorithm
- desired output
- fuzzy logic
- expert systems
- database
- bayesian learning
- network architecture
- maximum likelihood
- back propagation
- constraint satisfaction
- classification rules
- neural network model
- multilayer perceptron
- neural nets
- machine learning
- artificial intelligence
- global constraints
- artificial neural networks
- feedforward neural networks
- training data